3

I have a collection of images, for example, cats and dogs. I also have a CSV accompanying this. The CSV has metadata for the images like the weight of the animal.

I have made a classifier for the cats VS dogs images. How can I use the CSV with the metadata to improve this classifier? Do I need to make a separate classifier for the metadata and combine these two classifiers?

Sorry if this is a stupid question but I can't find anything online and I don't even know the term for what I am looking for.

Thank you for taking the time to read this

Null Pointer
  • 111
  • 1
  • 7

1 Answers1

3

Yes you can, in Keras you could use the functional API as explained in detail in this post.

Your code should look like this:

# define two sets of inputs
inputA = Input(shape=(32,))
inputB = Input(shape=(128,))

# the first branch operates on the first input
x = Dense(8, activation="relu")(inputA)
x = Dense(4, activation="relu")(x)
x = Model(inputs=inputA, outputs=x)

# the second branch opreates on the second input
y = Dense(64, activation="relu")(inputB)
y = Dense(32, activation="relu")(y)
y = Dense(4, activation="relu")(y)
y = Model(inputs=inputB, outputs=y)

# combine the output of the two branches
combined = concatenate([x.output, y.output])

# apply a FC layer and then a regression prediction on the
# combined outputs
z = Dense(2, activation="relu")(combined)
z = Dense(1, activation="linear")(z)

# our model will accept the inputs of the two branches and
# then output a single value
model = Model(inputs=[x.input, y.input], outputs=z)
Franco Piccolo
  • 6,845
  • 8
  • 34
  • 52